Isabelle Cudlitz
commited on
Commit
·
f12af66
1
Parent(s):
0b39a73
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3942,4 +3942,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3942 |
### Framework versions
|
| 3943 |
|
| 3944 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3945 |
- PEFT 0.6.2
|
|
|
|
| 3942 |
### Framework versions
|
| 3943 |
|
| 3944 |
|
| 3945 |
+
- PEFT 0.6.2
|
| 3946 |
+
## Training procedure
|
| 3947 |
+
|
| 3948 |
+
|
| 3949 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3950 |
+
- load_in_8bit: True
|
| 3951 |
+
- load_in_4bit: False
|
| 3952 |
+
- llm_int8_threshold: 6.0
|
| 3953 |
+
- llm_int8_skip_modules: None
|
| 3954 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3955 |
+
- llm_int8_has_fp16_weight: False
|
| 3956 |
+
- bnb_4bit_quant_type: fp4
|
| 3957 |
+
- bnb_4bit_use_double_quant: False
|
| 3958 |
+
- bnb_4bit_compute_dtype: float32
|
| 3959 |
+
|
| 3960 |
+
### Framework versions
|
| 3961 |
+
|
| 3962 |
+
|
| 3963 |
- PEFT 0.6.2
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21020682
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8452405462e1fffd9537e97e8acd3b4d5fa31de3a9d52a66274e98416a2518a
|
| 3 |
size 21020682
|